From: Tao Ma <boyu.mt@xxxxxxxxxx>
Now we stores data in the inode, but in case we need to store some
xattrs and inode doesn't have enough space, Andreas suggested that
we should keep the xattr(metadata) in and data should be pushed out.
So this patch does the work.
Signed-off-by: Tao Ma <boyu.mt@xxxxxxxxxx>
---
fs/ext4/inline.c | 46 ++++++++++++++++++++++++++++++++++++++++++----
fs/ext4/xattr.c | 48 +++++++++++++++++++++++++++++++++++++++++++++++-
fs/ext4/xattr.h | 9 ++++++---
3 files changed, 95 insertions(+), 8 deletions(-)
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index dcf1f8e..6a4053e 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -202,7 +202,7 @@ out:
/*
* write the buffer to the inline inode.
* If 'create' is set, we don't need to do the extra copy in the xattr
- * value since it is already handled by ext4_xattr_ibody_set. That saves
+ * value since it is already handled by ext4_xattr_ibody_inline_set. That saves
* us one memcpy.
*/
void ext4_write_inline_data(struct inode *inode, struct ext4_iloc *iloc,
@@ -280,7 +280,7 @@ static int ext4_create_inline_data(handle_t *handle,
BUG_ON(!is.s.not_found);
- error = ext4_xattr_ibody_set(handle, inode, &i, &is);
+ error = ext4_xattr_ibody_inline_set(handle, inode, &i, &is);
if (error) {
if (error == -ENOSPC)
ext4_clear_inode_state(inode,
@@ -349,7 +349,7 @@ static int ext4_update_inline_data(handle_t *handle, struct inode *inode,
i.value = value;
i.value_len = len;
- error = ext4_xattr_ibody_set(handle, inode, &i, &is);
+ error = ext4_xattr_ibody_inline_set(handle, inode, &i, &is);
if (error)
goto out;
@@ -422,7 +422,7 @@ static int ext4_destroy_inline_data_nolock(handle_t *handle,
if (error)
goto out;
- error = ext4_xattr_ibody_set(handle, inode, &i, &is);
+ error = ext4_xattr_ibody_inline_set(handle, inode, &i, &is);
if (error)
goto out;
@@ -1709,3 +1709,41 @@ out:
up_read(&EXT4_I(inode)->xattr_sem);
return (error < 0 ? error : 0);
}
+
+/*
+ * Called during xattr set, and if we can sparse space 'needed',
+ * just create the extent tree evict the data to the outer block.
+ *
+ * We use jbd2 instead of page cache to move data to the 1st block
+ * so that the whole transaction can be committed as a whole and
+ * the data isn't lost because of the delayed page cache write.
+ */
+int ext4_try_to_evict_inline_data(handle_t *handle,
+ struct inode *inode,
+ int needed)
+{
+ int error;
+ struct ext4_xattr_entry *entry;
+ struct ext4_xattr_ibody_header *header;
+ struct ext4_inode *raw_inode;
+ struct ext4_iloc iloc;
+
+ error = ext4_get_inode_loc(inode, &iloc);
+ if (error)
+ return error;
+
+ raw_inode = ext4_raw_inode(&iloc);
+ header = IHDR(inode, raw_inode);
+ entry = (struct ext4_xattr_entry *)((void *)raw_inode +
+ EXT4_I(inode)->i_inline_off);
+ if (EXT4_XATTR_LEN(entry->e_name_len) +
+ EXT4_XATTR_SIZE(le32_to_cpu(entry->e_value_size)) < needed) {
+ error = -ENOSPC;
+ goto out;
+ }
+
+ error = ext4_convert_inline_data_nolock(handle, inode, &iloc);
+out:
+ brelse(iloc.bh);
+ return error;
+}
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index dfcb156..e83beb2 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -959,6 +959,44 @@ int ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i,
return 0;
}
+int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode,
+ struct ext4_xattr_info *i,
+ struct ext4_xattr_ibody_find *is)
+{
+ struct ext4_xattr_ibody_header *header;
+ struct ext4_xattr_search *s = &is->s;
+ int error;
+
+ if (EXT4_I(inode)->i_extra_isize == 0)
+ return -ENOSPC;
+ error = ext4_xattr_set_entry(i, s);
+ if (error) {
+ if (error == -ENOSPC &&
+ ext4_has_inline_data(inode)) {
+ error = ext4_try_to_evict_inline_data(handle, inode,
+ EXT4_XATTR_LEN(strlen(i->name) +
+ EXT4_XATTR_SIZE(i->value_len)));
+ if (error)
+ return error;
+ error = ext4_xattr_ibody_find(inode, i, is);
+ if (error)
+ return error;
+ error = ext4_xattr_set_entry(i, s);
+ }
+ if (error)
+ return error;
+ }
+ header = IHDR(inode, ext4_raw_inode(&is->iloc));
+ if (!IS_LAST_ENTRY(s->first)) {
+ header->h_magic = cpu_to_le32(EXT4_XATTR_MAGIC);
+ ext4_set_inode_state(inode, EXT4_STATE_XATTR);
+ } else {
+ header->h_magic = cpu_to_le32(0);
+ ext4_clear_inode_state(inode, EXT4_STATE_XATTR);
+ }
+ return 0;
+}
+
int ext4_xattr_ibody_set(handle_t *handle, struct inode *inode,
struct ext4_xattr_info *i,
struct ext4_xattr_ibody_find *is)
@@ -1117,9 +1155,17 @@ ext4_xattr_set(struct inode *inode, int name_index, const char *name,
{
handle_t *handle;
int error, retries = 0;
+ int credits = EXT4_DATA_TRANS_BLOCKS(inode->i_sb);
retry:
- handle = ext4_journal_start(inode, EXT4_DATA_TRANS_BLOCKS(inode->i_sb));
+ /*
+ * In case of inline data, we may push out the data to a block,
+ * So reserve the journal space first.
+ */
+ if (ext4_has_inline_data(inode))
+ credits += ext4_writepage_trans_blocks(inode) + 1;
+
+ handle = ext4_journal_start(inode, credits);
if (IS_ERR(handle)) {
error = PTR_ERR(handle);
} else {
diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h
index 2e09ab2..ef9ce62 100644
--- a/fs/ext4/xattr.h
+++ b/fs/ext4/xattr.h
@@ -122,9 +122,9 @@ extern int ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i,
extern int ext4_xattr_ibody_get(struct inode *inode, int name_index,
const char *name,
void *buffer, size_t buffer_size);
-extern int ext4_xattr_ibody_set(handle_t *handle, struct inode *inode,
- struct ext4_xattr_info *i,
- struct ext4_xattr_ibody_find *is);
+extern int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode,
+ struct ext4_xattr_info *i,
+ struct ext4_xattr_ibody_find *is);
extern int ext4_has_inline_data(struct inode *inode);
extern int ext4_get_inline_size(struct inode *inode);
@@ -187,6 +187,9 @@ extern struct buffer_head *ext4_get_first_inline_block(struct inode *inode,
extern int ext4_inline_data_fiemap(struct inode *inode,
struct fiemap_extent_info *fieinfo,
int *has_inline);
+extern int ext4_try_to_evict_inline_data(handle_t *handle,
+ struct inode *inode,
+ int needed);
# else /* CONFIG_EXT4_FS_XATTR */
static inline int
--
1.7.1
--
To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
